© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116818
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     таких
    -0.08
     такие
    -0.07
     tipos
    -0.07
     types
    -0.07
     такой
    -0.07
     ছড়িয়ে
    -0.07
     greener
    -0.06
     어떤
    -0.06
                          
    -0.06
     such
    -0.06
    POSITIVE LOGITS
     त्यानंतर
    0.06
    Previous
    0.06
     রশ্ম
    0.05
     त्यामुळे
    0.05
     Previous
    0.05
     देण्यासाठी
    0.05
     precedente
    0.05
     subsequently
    0.05
     selanjutnya
    0.05
     previous
    0.05
    Activations Density 0.000%

    No Known Activations